Final Project Draft 3 11.28.2023

points2=read_csv("byYear2.csv")

## Rows: 5933 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): State, Year, Ban Status, Origin of Challenge
## dbl (1): banCount
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

points2=points2 %>%
  mutate(Year = as.factor(Year))

points2=points2 %>%
  filter(!State %in% c("Alabama", "Arizona", "Connecticut", "Delaware", "Hawaii", "Louisiana", "Montana", "Nevada", "New Mexico", "District of Columbia", "Puerto Rico"))

points2=points2 %>%
  arrange(desc(banCount))

pointsTopTen=points2 %>%
  filter(State %in% c("Florida", "Texas", "Pennsylvania", "Tennessee", "Missouri", "Utah", "South Carolina", "Virginia", "North Carolina", "Oklahoma"))

pointsTopTen=pointsTopTen %>%
  rename("statusBan" = `Ban Status`)

pointsTopTen=pointsTopTen %>%
  rename(challengeOrigin=`Origin of Challenge`)

pointsTopTen=pointsTopTen %>%
  mutate(statusBan = as.factor(statusBan),
         challengeOrigin = as.factor(challengeOrigin))

pointsTopTen=pointsTopTen %>%
  group_by(State) %>%
  add_count(statusBan)

pointsTopTen=pointsTopTen %>%
  rename(statusCount=n)

pointsTopTen=pointsTopTen %>%
  group_by(State) %>%
  add_count(challengeOrigin)

pointsTopTen=pointsTopTen %>%
  rename(originCount=n)

pointsTopTen %>%
  filter(State=="Oklahoma")

## # A tibble: 45 × 7
## # Groups:   State [1]
##    State    Year      statusBan challengeOrigin banCount statusCount originCount
##    <chr>    <fct>     <fct>     <fct>              <dbl>       <int>       <int>
##  1 Oklahoma 2021-2022 Banned P… Administrator         43          19          43
##  2 Oklahoma 2021-2022 Banned P… Administrator         43          19          43
##  3 Oklahoma 2021-2022 Banned i… Administrator         43           9          43
##  4 Oklahoma 2021-2022 Banned i… Administrator         43          12          43
##  5 Oklahoma 2021-2022 Banned i… Administrator         43          12          43
##  6 Oklahoma 2021-2022 Banned i… Administrator         43           9          43
##  7 Oklahoma 2021-2022 Banned P… Administrator         43          19          43
##  8 Oklahoma 2021-2022 Banned i… Administrator         43          12          43
##  9 Oklahoma 2021-2022 Banned i… Administrator         43          12          43
## 10 Oklahoma 2021-2022 Banned P… Administrator         43          19          43
## # ℹ 35 more rows

book_plot2=ggplot(pointsTopTen, aes(x=banCount, y= reorder(State, banCount)))+
  geom_point(aes(color=Year, text = paste0("State: ", State, "<br>", "Number of Bans: ", banCount)))+
  geom_line()+
  theme_minimal(base_size=11)+
  theme(panel.grid.major.y = element_blank(), panel.grid.major.x = element_line(color="lightgray"), panel.grid.minor.x = element_blank(), plot.caption = element_text(hjust = -0.2), text=element_text(family = "Times"))+
  scale_color_manual(name = "School Year", labels = c("2021-2022", "2022-2023"), values = c("#CCCCFF", "#73c6b6"))+
  scale_x_continuous(breaks = c(0,250,500,750,1000,1250,1500), labels = c("0","250","500","750","1000","1250","1500"))+
  labs(title = "Book bans on the rise", subtitle = "Top ten states with the most bans", y = "", x = "Number of Bans", caption = "Data from PEN America")

## Warning in geom_point(aes(color = Year, text = paste0("State: ", State, :
## Ignoring unknown aesthetics: text

ggsave("FinalBarBellBan.pdf")

## Saving 7 x 5 in image

ggplotly(book_plot2, tooltip = "text") %>%
    layout(title = list(text = paste0('Book bans on the rise',
                                    '<br>',
                                    '<sup>',
                                    'Top ten states with the most bans',
                                    '</sup>')),
         annotations = list(x = 1.18, y = 1.1, text = "Data from PEN America",
                            xref='paper', yref='paper', showarrow = F, 
                            xanchor='right', yanchor='auto', xshift=0, yshift=0,
                            font = list(size = 10)))

points3=read_csv("byYear2.csv")

## Rows: 5933 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): State, Year, Ban Status, Origin of Challenge
## dbl (1): banCount
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

points3=points3 %>%
  rename(challengeOrigin=`Origin of Challenge`)

points3=points3 %>%
  rename(statusBan = `Ban Status`)
points3=points3 %>%
  mutate(statusBan = as.factor(statusBan),
         challengeOrigin = as.factor(challengeOrigin))

points3=points3 %>%
  filter(!statusBan %in% c("No bans"))

points3 %>%
  group_by(State) %>%
  ggplot(aes(x=statusBan, fill = statusBan))+
  geom_bar()+
  theme_minimal(base_size=12)+
  theme(text=element_text(family = "Times"), legend.position = "none", plot.title = element_text(hjust = -1.5))+
  labs(title = "How are books banned in the United States?", x = "", y = "", caption = "Data from PEN America")+
  scale_fill_discrete_qualitative("Cold")+
  coord_flip()